Cheetah Speech-to-Text
React Native Quick Start

Platforms

• Android 5.0+ (API 21+)
• iOS 13.0+

Requirements

• Picovoice Account and AccessKey
• React Native 0.62.2+

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Setup the React Native environment.

2. Install the npm packages:

   • @picovoice/cheetah-react-native

npm install @picovoice/cheetah-react-native

3. Enable the proper permissions for recording with the hardware's microphone on both iOS and Android:

<key>NSMicrophoneUsageDescription</key>
<string>[Permission explanation]</string>

<uses-permission android:name="android.permission.RECORD_AUDIO" />
<uses-permission android:name="android.permission.INTERNET" />

Model File

Create a custom model using the Picovoice Console or use the default model.

Android

To add a Cheetah Streaming Speech-to-Text model file to your Android application, add the file as a bundled resource by placing it under the assets directory of your Android application.

iOS

To add a Cheetah Streaming Speech-to-Text model file to your iOS application, add the file as a bundled resource by selecting Build Phases in Xcode and adding it to the Copy Bundle Resources step.

Usage

Create an instance of Cheetah Streaming Speech-to-Text using a custom model from Picovoice console or a default model.

import { Cheetah, CheetahErrors } from '@picovoice/cheetah-react-native';

const accessKey = "{ACCESS_KEY}"  // AccessKey obtained from Picovoice Console (https://console.picovoice.ai/)
const modelPath = "{CHEETAH_MODEL_PATH}" // path relative to the assets folder or absolute path to file on device

try {
    const cheetah = await Cheetah.create(accessKey, modelPath)
} catch (err: any) {
  if (err instanceof CheetahErrors) {
    // handle error
  }
}

Transcribe real-time audio:

const getAudioFrame = () => {
  // get audio frames
}

const transcript = ""

try {
  while (1) {
    const partialResult = await cheetah.process(getAudioFrame())
    transcript += partialResult.transcript
    if (partialResult.isEndpoint) {
      const finalResult = await cheetah.flush()
      transcript += finalTranscript.transcript
    }
  }
} catch (err: any) {
  if (err instanceof CheetahErrors) {
    // handle error
  }
}

Free resources used by Cheetah Streaming Speech-to-Text:

cheetah.delete()

Non-English Languages

In order to use Cheetah with other languages, you need to use the corresponding model file (.pv) for the desired language. The model files for all supported languages are available on the Cheetah GitHub repository.

Demo

For the Cheetah Streaming Speech-to-Text React Native SDK, there is a React Native demo project available on the Picovoice GitHub repository.

Setup

Clone the Picovoice repository from GitHub:

git clone --recurse-submodules https://github.com/Picovoice/cheetah.git

Usage

1. Install dependencies and setup environment:

cd cheetah/demo/react-native

npm run android-install
# or
npm run ios-install

2. Connect a mobile device or launch a simulator and run:

npm run android-run
# or
npm run ios-run

For more information on our Cheetah Streaming Speech-to-Text demos for React Native, head over to our GitHub repository.

Resources